Training in progress, step 2500

config.json

@@ -1,7 +1,10 @@
 {
   "_commit_hash": null,
+  "architectures": [
+    "VisionEncoderDecoderModel"
+  ],
   "decoder": {
-    "_name_or_path": "imvladikon/alephbertgimmel-base-512",
+    "_name_or_path": "onlplab/alephbert-base",
     "add_cross_attention": true,
     "architectures": [
       "BertForMaskedLM"
@@ -76,13 +79,13 @@
     "torch_dtype": null,
     "torchscript": false,
     "transformers_version": "4.28.1",
-    "type_vocab_size": 2,
+    "type_vocab_size": 1,
     "typical_p": 1.0,
     "use_bfloat16": false,
     "use_cache": true,
-    "vocab_size": 128000
+    "vocab_size": 52000
   },
-  "decoder_start_token_id": 1,
+  "decoder_start_token_id": 2,
   "early_stopping": true,
   "encoder": {
     "_name_or_path": "google/vit-base-patch16-224-in21k",
@@ -164,15 +167,16 @@
     "typical_p": 1.0,
     "use_bfloat16": false
   },
-  "eos_token_id": 2,
+  "eos_token_id": 3,
   "is_encoder_decoder": true,
   "length_penalty": 2.0,
-  "max_length": 4,
+  "max_length": 5,
   "model_type": "vision-encoder-decoder",
   "no_repeat_ngram_size": 3,
   "num_beams": 4,
-  "pad_token_id": 3,
+  "pad_token_id": 0,
   "tie_word_embeddings": false,
+  "torch_dtype": "float32",
   "transformers_version": null,
-  "vocab_size": 128000
+  "vocab_size": 52000
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ee2c6f549fa2f9541b26b5c6f063fde015dcef40eba3af9c2a6c0bdd85fd98d
-size 1197111289
+oid sha256:865f5978fd554caffca001fca84089c3fd7a48e80f6bb909dc1dc2b50b6d88f9
+size 963332153

runs/May18_20-54-14_b5b0e8d5e2bb/1684443638.8033147/events.out.tfevents.1684443638.b5b0e8d5e2bb.31.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12a026e11d1694e4f0232c70b8539386976e0f82165b392fe4440200ee59dc7e
+size 6110

runs/May18_20-54-14_b5b0e8d5e2bb/events.out.tfevents.1684443638.b5b0e8d5e2bb.31.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96c999cc7f8678322f98fad10fcc5cf031ed58d38cb897fa3cad3f3025e0d7bd
+size 204958

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d415711f902130199574557cc354cc65dd6331dbfea11f02fb8b35dfb17c2866
+oid sha256:f9fa47d41396598585d7ce306df647931184ae087af3d20a550b324155b4e149
 size 3771